RichardErkhov/TheBlueObserver_-_Falcon3-7B-Instruct-MLX-gguf

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Falcon3-7B-Instruct-MLX - GGUF

• —Model creator: https://huggingface.co/TheBlueObserver/
• —Original model: https://huggingface.co/TheBlueObserver/Falcon3-7B-Instruct-MLX/

Original model description: --- base_model: tiiuae/Falcon3-7B-Instruct language:

• —en
• —fr
• —es
• —pt libraryname: transformers license: other licensename: falcon-llm-license license_link: https://falconllm.tii.ae/falcon-terms-and-conditions.html tags:
• —falcon3
• —mlx ---

TheBlueObserver/Falcon3-7B-Instruct-MLX

The Model TheBlueObserver/Falcon3-7B-Instruct-MLX was converted to MLX format from tiiuae/Falcon3-7B-Instruct using mlx-lm version 0.20.2.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("TheBlueObserver/Falcon3-7B-Instruct-MLX")

prompt="hello"

if hasattr(tokenizer, "apply_chat_template") and tokenizer.chat_template is not None:
    messages = [{"role": "user", "content": prompt}]
    prompt = tokenizer.apply_chat_template(
        messages, tokenize=False, add_generation_prompt=True
    )

response = generate(model, tokenizer, prompt=prompt, verbose=True)